CH

Chandra Ocr 2

ChandraGGUF by prithivMLmodsUpdated 2026-10-25
Download on Hugging Face
Parameters4.84B
Context256K
Layers32
Architectureqwen35
Smallest quant2.1 GB
Quick answer

Chandra Ocr 2 needs about 4.6 GB of memory at Q4_K_M (a 3.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 14 quants, from 2.1 GB (Q2_K) to 9.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Chandra OCR 2 – 4.8B Qwen 3.5 OCR model for structured document extraction

Chandra OCR 2 is a 4.8B parameter Qwen 3.5 model that extracts text, tables, math, and images from PDFs and images. It outputs markdown, HTML, or JSON while preserving layout. The model supports 90+ languages and includes handwriting and form recognition.

Good at

  • OCR of complex layouts
  • Multilingual text extraction
  • Table and math parsing

Limits

  • Vision only, no text‑to‑speech
  • Requires 8k context for full features
  • License restricts competitive use

Best for

  • Document digitization pipelines
  • Form and invoice processing
  • Research paper conversion

Who it’s for. Developers building OCR or document‑analysis applications that need accurate layout preservation and multilingual support. The model is suitable for research, startups, and small‑business use under the license terms.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.1 GB 3.7 GB
Fits Get file →
Q3_K_S2.3 GB 3.9 GB
Fits Get file →
Q3_K_M2.5 GB 4.1 GB
Fits Get file →
Q3_K_L2.7 GB 4.3 GB
Fits Get file →
Q4_02.9 GB 4.5 GB
Fits Get file →
Q4_K_S2.9 GB 4.5 GB
Fits Get file →
Q4_K_M3.1 GB 4.6 GB
Fits Get file →
Q5_03.4 GB 5.0 GB
Fits Get file →
Q5_K_S3.4 GB 5.0 GB
Fits Get file →
Q5_K_M3.5 GB 5.1 GB
Fits Get file →
Q6_K4.0 GB 5.6 GB
Fits Get file →
Q8_05.2 GB 6.7 GB
Fits Get file →
BF169.7 GB 11.3 GB
Too big Get file →
F169.7 GB 11.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (3.07 GB) or Q5_K_S (3.43 GB). If 12 GB VRAM is available, Q6_K (3.99 GB) or Q8_0 (5.16 GB) provide higher quality. Memory estimates are approximate and assume 8k context.

What GPU do you need for Chandra Ocr 2?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is Q3_K_S (2.3 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (4.0 GB file, about 5.6 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (5.2 GB file, about 6.7 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (9.7 GB file, about 11.3 GB in use).

Which Chandra Ocr 2 quant should you choose?

Q4_K_M is the usual starting point for Chandra Ocr 2: it balances file size and quality well. Here it is a 3.1 GB file.

The Q8_0 file is 5.2 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 2.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters4.84B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byprithivMLmods
FamilyChandra
Licenseother
Downloads (HF)16,128
Last updated2026-10-25

Frequently asked questions about Chandra Ocr 2

How much VRAM does Chandra Ocr 2 need?

About 4.6 GB at Q4_K_M with an 8K context window. That is the 3.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Chandra Ocr 2 on an 8 GB GPU?

Yes, with Q8_0: the 5.2 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Chandra Ocr 2 GGUF?

It depends on the quant: Q2_K is 2.1 GB, Q3_K_S is 2.3 GB, Q3_K_M is 2.5 GB, Q3_K_L is 2.7 GB, Q4_0 is 2.9 GB, Q4_K_S is 2.9 GB and 8 more.

What context length does Chandra Ocr 2 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Chandra Ocr 2 GGUF?

The files are on Hugging Face in the prithivMLmods/chandra-ocr-2-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Chandra Ocr 2 use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Chandra OCR 2 on 8 GB VRAM?

Yes, with Q4_K_M or Q5_K_S quants, which fit within 8 GB VRAM and use about 4–5 GB of memory at 8k context.

Does the model support image captioning?

Yes, it includes improved image captioning and diagram extraction as part of its OCR output.

Is the model available for commercial use?

The weights are under a modified OpenRAIL‑M license, free for research and startups under $2M; commercial use requires separate licensing.

Other GGUFs of chandra-ocr-2

Similar models

Browse all →

More from prithivMLmods

All by prithivMLmods →

More Chandra models

All Chandra →

Other small models

All small models →